CN110809066A - IPv6 address generation model creation method, device and address generation method - Google Patents
IPv6 address generation model creation method, device and address generation method Download PDFInfo
- Publication number
- CN110809066A CN110809066A CN201910943931.8A CN201910943931A CN110809066A CN 110809066 A CN110809066 A CN 110809066A CN 201910943931 A CN201910943931 A CN 201910943931A CN 110809066 A CN110809066 A CN 110809066A
- Authority
- CN
- China
- Prior art keywords
- ipv6 address
- segment
- ipv6
- segments
- generation model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/50—Address allocation
- H04L61/5007—Internet protocol [IP] addresses
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L2101/00—Indexing scheme associated with group H04L61/00
- H04L2101/60—Types of network addresses
- H04L2101/618—Details of network addresses
- H04L2101/659—Internet protocol version 6 [IPv6] addresses
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention provides an IPv6 address generation model creating method, an IPv6 address generation model creating device and an address generation method, wherein the method comprises the following steps: counting the occurrence frequency of different values on each address bit in the IPv6 address according to a plurality of collected IPv6 addresses, and calculating the uncertainty of each address bit value according to the occurrence frequency of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; clustering the value space of each segmentation segment of the IPv6 address respectively to obtain the probability distribution of all clustering clusters in each segmentation segment; and constructing and training an IPv6 address generation model according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment. The IPv6 address generation model creation method provided by the embodiment of the invention can automatically create the IPv6 address generation model with higher survival rate, effectively improve the working efficiency and save manpower and material resources.
Description
Technical Field
The invention relates to the technical field of network security, in particular to an IPv6 address generation model creation method, an IPv6 address generation model creation device and an address generation method.
Background
In the IPv6 asset exploration, an IPv6 address, particularly a surviving IPv6 address, is obtained first. The IPv6 address that is alive refers to an IPv6 address used by a user. Because the IPv6 address has 128 bits in total, the address space range is extremely large, and the method cannot acquire the alive IPv6 address by adopting the exhaustion method which is common in the conventional IPv4 address period. A reliable IPv6 address candidate set with high survival rate needs to be generated in an intelligent manner through a certain strategy.
Currently, few researches and works are carried out on the aspect, mainly some theoretical researches are carried out, and practical verification is lacked. In commercial application, a plurality of candidate IPv6 address sets are generated by human experts mainly according to experience, and the stability and the survival rate of IPv6 addresses obtained by the method are low and the efficiency is low.
Disclosure of Invention
The embodiment of the invention provides an IPv6 address generation model creation method, an IPv6 address generation model creation device and an address generation method, which are used for solving the defects of low IPv6 address stability, low survival rate and low efficiency caused by searching for a survival IPv6 address mainly in a manual mode in the prior art and realizing the quick and efficient searching for the survival IPv6 address.
In a first aspect, an embodiment of the present invention provides a method for creating an IPv6 address generation model, including:
counting the occurrence frequency of different values on each address bit in the IPv6 address according to a plurality of collected IPv6 addresses, and calculating the uncertainty of each address bit value according to the occurrence frequency of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; wherein, the uncertainty of each address bit value in the same segmentation segment is close;
clustering the value space of each segmentation segment of the IPv6 address respectively to obtain the probability distribution of all clustering clusters in each segmentation segment;
according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment, constructing and training an IPv6 address generation model; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments.
Based on any of the above embodiments of the present invention, the method further includes: collecting IPv6 addresses, and obtaining the collected IPv6 addresses.
Based on any of the embodiments of the present invention, the value space of each segment of the IPv6 address is clustered by using a density clustering algorithm, so as to obtain the probability distribution of all clusters in each segment.
Based on any embodiment of the invention, an IPv6 address generation model based on the Bayesian network is constructed and trained according to the segments of the IPv6 address and the probability distribution of all cluster clusters in each segment.
Based on any of the above embodiments of the present invention, according to the segments of the IPv6 address and the probability distribution of all cluster clusters in each segment, a bayesian network-based IPv6 address generation model is constructed and trained, including:
constructing a Bayesian network structure, wherein the Bayesian network structure reflects the segments contained in the IPv6 address and the incidence relation among the segments;
constructing a probability distribution model of the Bayesian network structure, wherein the probability distribution model reflects the dependency relationship among the segmentation sections; and training the probability distribution model according to the probability distribution of all the clustering clusters in each segmentation segment, so that the parameters in the probability distribution model conform to the probability distribution of all the clustering clusters in each segmentation segment, and obtaining the conditional probability value between the segmentation segments.
Based on any of the above embodiments of the present invention, the uncertainty of each address bit value is described by using an information entropy, and the larger the entropy value of the information entropy is, the larger the uncertainty is;
the information entropy is used for partitioning the IPv6 address, and the position with large change of the information entropy value of adjacent address bits is taken as a partitioning point, and the method comprises the following steps: finding out the maximum difference a between the information entropies of all adjacent address bits in the IPv6 address, taking 1/2 of a as a partition threshold value, and taking the position between the two adjacent address bits as a partition point if the information entropy change condition of the two adjacent address bits exceeds the partition threshold value;
the uncertainty of the values of the address bits in the same partition is close, which means that the difference of the information entropies of the adjacent address bits in the same partition is smaller than the partition threshold.
The IPv6 address generation model creation method provided by the embodiment of the invention can be used for segmenting the IPv6 address and finding out the relation among all segments in the IPv6 address by analyzing the existing survival IPv6 address, and the IPv6 address generation model with higher survival rate can be automatically created by utilizing the relation, so that the working efficiency can be effectively improved, and the manpower and material resources can be saved.
In a second aspect, an embodiment of the present invention provides an IPv6 address generating method, including:
determining the segmentation segment contained in the IPv6 address to be generated according to the IPv6 address generation model obtained by the IPv6 address generation model creation method;
determining a value of the segment; wherein the value of a segment is determined by the values of the preceding segments with which it is associated and the corresponding conditional probabilities; the conditional probability is the probability of the value of the segment under the condition that the value of the prior segment occurs, and the value of the conditional probability is obtained from the IPv6 address generation model obtained by the IPv6 address generation model creation method;
after the values of all the segments are determined, the segments are combined in sequence to form the IPv6 address.
The IPv6 address generation method provided by the embodiment of the invention utilizes an IPv6 address generation model which is obtained by analyzing the existing survival IPv6 address and contains the internal rule among the survival IPv6 address segmentation segments, so that the IPv6 address with higher survival rate can be automatically generated, the efficiency and the asset scale of network asset exploration are effectively improved, and manpower and material resources are saved.
In a third aspect, an embodiment of the present invention provides an IPv6 address generation model creating apparatus, including:
the IPv6 address segmentation module is used for counting the occurrence frequency of different values on each address bit in the IPv6 address according to the collected multiple IPv6 addresses, and calculating the uncertainty of each address bit value according to the occurrence frequency of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; wherein, the uncertainty of each address bit value in the same segmentation segment is close;
the clustering module is used for respectively clustering the value space of each segmentation segment of the IPv6 address to obtain the probability distribution of all clustering clusters in each segmentation segment;
the IPv6 address generation model training module is used for constructing and training an IPv6 address generation model according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments.
Based on any of the above embodiments of the present invention, the method further includes: and the IPv6 address collection module collects IPv6 addresses and obtains the collected multiple IPv6 addresses.
Based on any of the embodiments of the present invention, the clustering module uses a density clustering algorithm to cluster the value space of each segment of the IPv6 address, so as to obtain the probability distribution of all clusters in each segment.
Based on any of the embodiments of the present invention, the IPv6 address generation model training module constructs and trains a bayesian network-based IPv6 address generation model according to the segments of the IPv6 address and the probability distribution of all cluster clusters in each segment.
Based on any of the above embodiments of the present invention, the IPv6 address generation model training module constructs and trains a bayesian network-based IPv6 address generation model according to the segments of the IPv6 address and the probability distribution of all cluster clusters in each segment, including:
constructing a Bayesian network structure, wherein the Bayesian network structure reflects the segments contained in the IPv6 address and the incidence relation among the segments;
constructing a probability distribution model of the Bayesian network structure, wherein the probability distribution model reflects the dependency relationship among the segmentation sections; and training the probability distribution model according to the probability distribution of all the clustering clusters in each segmentation segment, so that the parameters in the probability distribution model conform to the probability distribution of all the clustering clusters in each segmentation segment, and obtaining the conditional probability value between the segmentation segments.
Based on any one of the above embodiments of the present invention, the IPv6 address segmentation module describes uncertainty of a value of each address bit by using an information entropy, and the larger the entropy of the information entropy is, the larger the uncertainty is;
the information entropy is used for partitioning the IPv6 address, and the position with large change of the information entropy value of adjacent address bits is taken as a partitioning point, and the method comprises the following steps: finding out the maximum difference a between the information entropies of all adjacent address bits in the IPv6 address, taking 1/2 of a as a partition threshold value, and taking the position between the two adjacent address bits as a partition point if the information entropy change condition of the two adjacent address bits exceeds the partition threshold value;
the uncertainty of the values of the address bits in the same partition is close, which means that the difference of the information entropies of the adjacent address bits in the same partition is smaller than the partition threshold.
The IPv6 address generation model creation device provided by the embodiment of the invention divides the IPv6 address and finds out the relation among all the divided sections in the IPv6 address by analyzing the existing survival IPv6 address, and the IPv6 address generation model with higher survival rate can be automatically created by utilizing the relation, so that the working efficiency can be effectively improved, and the manpower and material resources can be saved.
In a fourth aspect, an embodiment of the present invention provides an IPv6 address generating apparatus, including:
a segmentation segment generation module, configured to determine a segmentation segment included in the IPv6 address to be generated according to the IPv6 address generation model obtained by the IPv6 address generation model creation device;
a segment-valued module to determine a value of the segment; wherein the value of a segment is determined by the values of the preceding segments with which it is associated and the corresponding conditional probabilities; the conditional probability is the probability of the value of the segment under the condition that the value of the previous segment occurs, and the value of the conditional probability is obtained from the IPv6 address generation model obtained by the IPv6 address generation model creating device;
and the segmentation section combination module is used for combining the segmentation sections according to the sequence after the values of all the segmentation sections are determined to form the IPv6 address.
The IPv6 address generating device provided by the embodiment of the invention utilizes an IPv6 address generating model which is obtained by analyzing the existing survival IPv6 address and contains the internal rule among the survival IPv6 address segmentation segments, so that the IPv6 address with higher survival rate can be automatically generated, the efficiency and the asset scale of network asset exploration are effectively improved, and manpower and material resources are saved.
In a fifth aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the IPv6 address generation model creation method or implements the steps of the IPv6 address generation method when executing the program.
In a sixth aspect, embodiments of the present invention provide a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the IPv6 address generation model creation method as described, or implements the steps of the IPv6 address generation method as described.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for creating an IPv6 address generation model according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an IPv6 address partitioning sample provided by the embodiment of the present invention;
FIG. 3 is a diagram illustrating a segmentation clustering example according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a bayesian network structure established by each partition in the IPv6 address partition sample shown in fig. 2 according to the embodiment of the present invention;
fig. 5 is a flowchart of a method for creating an IPv6 address generation model according to another embodiment of the present invention;
fig. 6 is a flowchart of an IPv6 address generation method according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an IPv6 address generation model creation apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an IPv6 address generating apparatus according to an embodiment of the present invention;
fig. 9 illustrates a physical structure diagram of an electronic device.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of a method for creating an IPv6 address generation model according to an embodiment of the present invention, and as shown in fig. 1, to solve the above problem, an embodiment of the present invention provides a method for creating an IPv6 address generation model, where the method includes:
step 101, counting the occurrence frequency of different values on each address bit in the IPv6 address according to a plurality of collected IPv6 addresses, and calculating the information entropy of each address bit according to the occurrence frequency of the different values; then, partitioning the IPv6 address according to the information entropy of each address bit in the IPv6 address to obtain a plurality of partitions; and the entropy values of the information of the address positions in the same segmentation section are relatively close.
In the embodiment of the present invention, the collected IPv6 addresses should be surviving IPv6 addresses, at least IPv6 addresses with high survival rate.
Counting the frequency of occurrence of different values on each address bit in the IPv6 address, taking a 16-system expression mode common in IPv6 addresses as an example, possible values of each address bit include 0-F (i.e., 0-9 and a-F for expressing 10-15). Assuming that 10000 collected IPv6 addresses exist in the step, respectively counting the number of IPv6 addresses whose value is 0 at the 0 th address bit, the number of IPv6 addresses whose value is 1, the number of … … addresses, and the number of IPv6 addresses whose value is F in the 10000 IPv6 addresses, thereby obtaining the occurrence probability of different values at the 0 th address bit; by analogy, the occurrence probability of different values on the 1 st address bit, the occurrence probability of different values on the 2 nd address bit, and the occurrence probabilities of different values on the … … and the 127 th address bit can be obtained respectively.
After the occurrence frequency of different values on each address bit in the IPv6 address is obtained, the information entropy of each address bit can be calculated according to this probability. The information entropy is a measurement mode of uncertainty, and the larger the entropy value is, the larger the uncertainty is; the average uncertainty of the source should be single symbol uncertainty-log piThe statistical average value (E) calculated, i.e. the information entropy. The calculation formula of the information entropy is as follows:
wherein H (U) represents information entropy, E [ 2 ]]Denotes the mean value, piThe value of the address bit is 16-ary in the embodiment of the invention, so that the value of n is 16.
By describing the information amount of each bit of the IPv6 address by using the information entropy, the association relationship between data and the degree of difference between adjacent address bits can be obtained. Therefore, the dividing point can be determined by using the change situation of the entropy value of the information of the adjacent address bits in the IPv6 address. In the embodiment of the present invention, the following method may be adopted to determine the segmentation point: finding out the maximum difference a between the information entropies of adjacent address bits in the IPv6 address, taking 1/2 of a as a segmentation threshold, then comparing the information entropy change conditions of two adjacent address bits with the segmentation threshold, and if the information entropy change conditions of two adjacent address bits exceed the segmentation threshold, considering that the two adjacent address bits are the segmentation point.
After all the segmentation points in the IPv6 address are determined, the IPv6 address can be segmented to obtain a plurality of segmentation segments. Because the information entropy change condition of the adjacent address bits is referred to in the segmentation, the information entropy of the address bits in the same segment is relatively close in the same segment, such as in a segmentation threshold range generally.
Fig. 2 is a schematic diagram of an IPv6 address partitioning sample provided by an embodiment of the present invention, where fig. 2(a) is a schematic diagram of partitioning an IPv6 address based on information entropy, and the horizontal axis in fig. 2(a) is 128 bits of the IPv6 address, and the vertical axis is an information entropy value calculated according to the frequency of occurrence of data in each bit. The fluctuation of information entropy in fig. 2(a) divides IPv6 addresses into a-K segments. Fig. 2(b) is a schematic diagram of the probability of occurrence of some values corresponding to the segments, and it can be seen from fig. 2(b) that the stability of the address bit values in different segments is different, for example, in the segment a, the address bit value 20010db8 is stable and unchanged; the values of the address bits in the section C can be 10, 22, 20 and 21, and the values have different occurrence probabilities.
And 102, clustering the value space of each segment of the IPv6 address respectively to obtain the probability distribution of all cluster clusters in each segment.
In the embodiment of the invention, the clustering operation is realized by adopting a density clustering algorithm. When clustering is performed according to a density clustering algorithm, points in a region are added to clusters that are close to the points as long as the density of the points exceeds a certain threshold. In the specific implementation, one of density clustering algorithms such as a DBSCAN algorithm, an OPTICS algorithm, a DENCLUE algorithm and the like can be adopted.
Fig. 3 is a schematic diagram of a segmentation segment clustering example provided in an embodiment of the present invention, where a segmentation segment in the example includes 2 16-ary bits, and there are 256 possible value spaces in total, so that the horizontal axis in the diagram represents the 256 possible value spaces, and the vertical axis represents the frequency of occurrence of each value on the segmentation segment obtained by counting a plurality of collected IPv6 addresses. In the example shown in fig. 3, the segments are clustered to form 7 cluster clusters.
103, constructing and training an IPv6 address generation model according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments.
In the embodiment of the invention, the IPv6 address generation model is realized based on a Bayesian network. The Bayesian network originates from the research in the field of artificial intelligence, is a tool for applying probability statistics to complex systems and carrying out uncertainty inference and data analysis, and is a product of combining probability theory and graph theory. The Bayesian network is a probability graph model based on Bayesian theorem, and can be expressed as BN < < V, E >, P >. The network structure is denoted by < V, E >, and is a directed acyclic graph, V is a network node, E is a directed edge between nodes, and E denotes a Conditional Probability Table (CPT).
In specific implementation, first, a bayesian network structure is constructed.
The Bayesian network structure reflects the segments contained in the IPv6 address and the association relationship among the segments. Fig. 4 is a schematic diagram of a bayesian network structure established by each partition in the IPv6 address partition sample shown in fig. 2. This bayesian network structure reflects which segments of a-segment K are independent and which have a relationship between them.
Then, a probability distribution model of the Bayesian network structure is constructed, and the probability distribution model is trained according to the probability distribution of all the cluster clusters in each segment, so that parameters in the probability distribution model conform to the probability distribution of all the cluster clusters in each segment, and conditional probability values among the segments are obtained.
The Bayesian network structure established before can only reflect which segments have association relations, and cannot reflect the degree of association. The relevance degree is represented by a probability distribution model, parameters in the probability distribution model are adjusted by the known probability distribution of all cluster clusters in each segmentation segment, and when the parameters in the probability distribution model accord with the probability distribution of all cluster clusters in each segmentation segment, the conditional probability values among the segmentation segments can be obtained by the parameters in the probability distribution model.
In the embodiment of the invention, the IPv6 address generation model is constructed and trained on the basis of the Bayesian network, and in other embodiments of the invention, the IPv6 address generation model can also be constructed and trained on the basis of other methods, such as a recurrent neural network method.
The above is a description of implementation steps of the IPv6 address generation model creation method provided in the embodiment of the present invention. The IPv6 address generation model creation method provided by the embodiment of the invention can be used for segmenting the IPv6 address and finding out the relation among all segments in the IPv6 address by analyzing the existing survival IPv6 address, and the IPv6 address generation model with higher survival rate can be automatically created by utilizing the relation, so that the working efficiency can be effectively improved, and the manpower and material resources can be saved.
Based on any of the above embodiments, fig. 5 is a flowchart of a method for creating an IPv6 address generation model according to another embodiment of the present invention, and as shown in fig. 5, the method for creating an IPv6 address generation model according to another embodiment of the present invention includes:
and step 501, collecting IPv6 addresses to obtain a plurality of collected IPv6 addresses.
In the embodiment of the invention, the IPv6 address collection adopts a network traffic analysis mode. Currently, there are three main ways for analyzing network traffic: SNMP traffic analysis, network probe-based traffic analysis, and real-time traffic packet capture-based data analysis. All three ways can be used in the embodiment of the present invention to realize the collection of the surviving IPv6 addresses. The IPv6 addresses with higher survival rate can be collected by adopting a network traffic analysis mode to collect the IPv6 addresses.
In other embodiments of the present invention, the surviving IPv6 address may also be obtained by means known to those skilled in the art, such as obtaining a surviving IPv6 address set from a third party authority.
502, counting the occurrence frequency of different values on each address bit in the IPv6 address according to a plurality of collected IPv6 addresses, and calculating the information entropy of each address bit according to the occurrence frequency of the different values; and then, partitioning the IPv6 address according to the information entropy of each address bit in the IPv6 address to obtain a plurality of partitions.
The steps 502 to 504 are not substantially different from the steps 101 to 103 in the details of implementation, and therefore are not described repeatedly here.
The IPv6 address generation model creation method provided by the embodiment of the invention adopts a network traffic analysis method to obtain the survival IPv6 address for analysis, so that the survival rate of the IPv6 address generated by the finally generated IPv6 address generation model is higher.
Based on any of the above embodiments, fig. 6 is a flowchart of an IPv6 address generation method provided by the embodiment of the present invention, and as shown in fig. 6, the IPv6 address generation method provided by the embodiment of the present invention includes:
601, determining a segmentation segment contained in the IPv6 address to be generated according to the IPv6 address generation model obtained by the IPv6 address generation model creation method;
from the IPv6 address generation model obtained previously, it is possible to know how many segments an IPv6 address contains, and thus the number of segments constituting an IPv6 address, the number of address bits in each segment, and the sequential relationship between the segments can be determined. In this case, the value of each address bit in each segment may be set to 0 or any other specified value.
As known from the IPv6 address generation model, some segments are independent, such as the segment a, the segment B, and the segment K in fig. 4, and these independent segments are usually the case where the network prefix or other values are constant, so that the values of these segments are determined and can be directly assigned according to the determined values. Some segments have an association relationship, for example, when assigning a value to the segment C, the segment C can be assigned a value with a higher probability according to the probability provided by the IPv6 address generation model, and then the segment D can be assigned a value. For example, suppose segment C is a segment of length 3 (having 3 address bits) and segment D is a segment of length 2. The C segment has 8 cluster clusters, a numerical value in one cluster is randomly extracted according to the probability distribution of the cluster clusters, for example, the value of 0f6 in the C3 cluster is selected as an initial value, and then the values of other segmentation segments are deduced according to the IPv6 address generation model. Taking the D segment as an example, the probability relationship between the segments is obtained according to the IPv6 address generation model, for example, when the C segment selects the C3 cluster, the probability of the D1 cluster in the D segment (assuming that there are 5 cluster clusters) occurring is the highest (for example, 50%) and then it is very likely to select a value, for example, 0f, from the D1 according to the IPv6 address generation model as the generation value of the D segment. By analogy, the values of the individual segments can be determined.
And step 603, after all the segmentation segment values are determined, combining the segmentation segments according to the sequence to form the IPv6 address.
Knowing the sequential relationship between the segments, after determining the values of the segments, the segments can be combined in sequence to form the IPv6 address. The IPv6 address formed by the method has high survival rate.
The IPv6 address generation method provided by the embodiment of the invention utilizes an IPv6 address generation model which is obtained by analyzing the existing survival IPv6 address and contains the internal rule among the survival IPv6 address segmentation segments, so that the IPv6 address with higher survival rate can be automatically generated, the efficiency and the asset scale of network asset exploration are effectively improved, and manpower and material resources are saved.
Based on any of the above embodiments, fig. 7 is a schematic structural diagram of an IPv6 address generation model creation apparatus according to an embodiment of the present invention, and as shown in fig. 7, an IPv6 address generation model creation apparatus according to an embodiment of the present invention includes:
an IPv6 address partitioning module 701, configured to count occurrence frequencies of different values at each address bit in an IPv6 address according to the collected multiple IPv6 addresses, and calculate an uncertainty of each address bit value from the occurrence frequencies of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; and the uncertainty of the value of each address bit in the same segmentation segment is close.
In the embodiment of the present invention, the IPv6 address segmentation module 701 describes uncertainty of each address bit value by using an information entropy, where the larger the entropy of the information entropy is, the larger the uncertainty is. The calculation formula of the information entropy is as follows:
wherein H (U) represents information entropy, E [ 2 ]]Denotes the mean value, piThe value of the address bit is 16-ary in the embodiment of the invention, so that the value of n is 16.
The IPv6 address segmentation module 701 segments an IPv6 address according to the information entropy, and uses a position with a large change in information entropy of adjacent address bits as a segmentation point, including: finding out the maximum difference a between the information entropies of each adjacent address bit in the IPv6 address, taking 1/2 of a as a division threshold value, and taking the position between the two adjacent address bits as a division point when the information entropy change of the two adjacent address bits exceeds the division threshold value.
And the clustering module 702 is configured to cluster the value spaces of the segments of the IPv6 address, respectively, to obtain probability distributions of all clusters in each segment.
In the embodiment of the present invention, the clustering module 702 uses a density clustering algorithm to cluster the value space of each segment of the IPv6 address.
An IPv6 address generation model training module 703, configured to construct and train an IPv6 address generation model according to the segments of the IPv6 address and the probability distribution of all cluster clusters in each segment; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments.
In this embodiment of the present invention, the IPv6 address generation model training module 703 is configured to build and train the IPv6 address generation model based on a bayesian network technology, and specifically includes: constructing a Bayesian network structure, wherein the Bayesian network structure reflects the segments contained in the IPv6 address and the incidence relation among the segments; constructing a probability distribution model of the Bayesian network structure, wherein the probability distribution model reflects the dependency relationship among the segmentation sections; and training the probability distribution model according to the probability distribution of all the clustering clusters in each segmentation segment, so that the parameters in the probability distribution model conform to the probability distribution of all the clustering clusters in each segmentation segment, and obtaining the conditional probability value between the segmentation segments.
The IPv6 address generation model creation device provided by the embodiment of the invention divides the IPv6 address and finds out the relation among all the divided sections in the IPv6 address by analyzing the existing survival IPv6 address, and the IPv6 address generation model with higher survival rate can be automatically created by utilizing the relation, so that the working efficiency can be effectively improved, and the manpower and material resources can be saved.
Based on any of the foregoing embodiments, an IPv6 address generation model creation apparatus according to another embodiment of the present invention further includes: an IPv6 address collection module that collects IPv6 addresses, resulting in the collected plurality of IPv6 addresses.
Based on any of the above embodiments, fig. 8 is a schematic structural diagram of an IPv6 address generating device according to an embodiment of the present invention, and as shown in fig. 8, an IPv6 address generating device according to an embodiment of the present invention includes:
a segmentation segment generation module 801, configured to determine a segmentation segment included in the IPv6 address to be generated according to the IPv6 address generation model obtained by the IPv6 address generation model creation apparatus;
a segment-valued module 802 for determining a value of the segment; wherein the value of a segment is determined by the values of the preceding segments with which it is associated and the corresponding conditional probabilities; the conditional probability is the probability of the value of the segment occurring under the condition that the value of the preceding segment occurs, and the value of the conditional probability is obtained from the IPv6 address generation model obtained by the IPv6 address generation model creation means;
and the segmentation combination module 803 is used for combining all the segments in sequence after the values of all the segments are determined to form the IPv6 address.
The IPv6 address generating device provided by the embodiment of the invention utilizes an IPv6 address generating model which is obtained by analyzing the existing survival IPv6 address and contains the internal rule among the survival IPv6 address segmentation segments, so that the IPv6 address with higher survival rate can be automatically generated, the efficiency and the asset scale of network asset exploration are effectively improved, and manpower and material resources are saved.
Fig. 9 illustrates a physical structure diagram of an electronic device, and as shown in fig. 9, the electronic device may include: a processor (processor)910, a communication Interface (Communications Interface)920, a memory (memory)930, and a communication bus 940, wherein the processor 910, the communication Interface 920, and the memory 930 communicate with each other via the communication bus 940. Processor 910 may invoke logic instructions in memory 930 to perform the following method: counting the occurrence frequency of different values on each address bit in the IPv6 address according to a plurality of collected IPv6 addresses, and calculating the uncertainty of each address bit value according to the occurrence frequency of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; clustering the value space of each segmentation segment of the IPv6 address respectively to obtain the probability distribution of all clustering clusters in each segmentation segment; according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment, constructing and training an IPv6 address generation model; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments. Or performing the following method: determining a segmentation segment contained in an IPv6 address to be generated according to an IPv6 address generation model; determining a value of the segment; after the values of all the segments are determined, the segments are combined in sequence to form the IPv6 address.
Furthermore, the logic instructions in the memory 930 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to perform the method provided by the foregoing embodiments, for example, including: counting the occurrence frequency of different values on each address bit in the IPv6 address according to a plurality of collected IPv6 addresses, and calculating the uncertainty of each address bit value according to the occurrence frequency of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; clustering the value space of each segmentation segment of the IPv6 address respectively to obtain the probability distribution of all clustering clusters in each segmentation segment; according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment, constructing and training an IPv6 address generation model; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments. Or comprises the following steps: determining a segmentation segment contained in an IPv6 address to be generated according to an IPv6 address generation model; determining a value of the segment; after the values of all the segments are determined, the segments are combined in sequence to form the IPv6 address.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (16)
1. An IPv6 address generation model creation method is characterized by comprising the following steps:
counting the occurrence frequency of different values on each address bit in the IPv6 address according to a plurality of collected IPv6 addresses, and calculating the uncertainty of each address bit value according to the occurrence frequency of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; wherein, the uncertainty of each address bit value in the same segmentation segment is close;
clustering the value space of each segmentation segment of the IPv6 address respectively to obtain the probability distribution of all clustering clusters in each segmentation segment;
according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment, constructing and training an IPv6 address generation model; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments.
2. The IPv6 address generation model creation method according to claim 1, further comprising: collecting IPv6 addresses, and obtaining the collected IPv6 addresses.
3. The IPv6 address generation model creation method of claim 1 or 2, characterized in that a density clustering algorithm is used to cluster the value space of each segment of the IPv6 address to obtain the probability distribution of all cluster clusters in each segment.
4. The IPv6 address generation model creation method according to claim 1 or 2, wherein a Bayesian network-based IPv6 address generation model is constructed and trained according to the segments of the IPv6 address and the probability distribution of all cluster clusters within each segment.
5. The IPv6 address generation model creation method of claim 4, wherein constructing and training a Bayesian network-based IPv6 address generation model according to the segments of IPv6 addresses and the probability distribution of all cluster clusters within each segment comprises:
constructing a Bayesian network structure, wherein the Bayesian network structure reflects the segments contained in the IPv6 address and the incidence relation among the segments;
constructing a probability distribution model of the Bayesian network structure, wherein the probability distribution model reflects the dependency relationship among the segmentation sections; and training the probability distribution model according to the probability distribution of all the clustering clusters in each segmentation segment, so that the parameters in the probability distribution model conform to the probability distribution of all the clustering clusters in each segmentation segment, and obtaining the conditional probability value between the segmentation segments.
6. The IPv6 address generation model creation method according to claim 1 or 2, wherein the uncertainty of each address bit value is described by using an information entropy, and the larger the entropy value of the information entropy is, the larger the uncertainty is;
the information entropy is used for partitioning the IPv6 address, and the position with large change of the information entropy value of adjacent address bits is taken as a partitioning point, and the method comprises the following steps: finding out the maximum difference a between the information entropies of all adjacent address bits in the IPv6 address, taking 1/2 of a as a partition threshold value, and taking the position between the two adjacent address bits as a partition point if the information entropy change condition of the two adjacent address bits exceeds the partition threshold value;
the uncertainty of the values of the address bits in the same partition is close, which means that the difference of the information entropies of the adjacent address bits in the same partition is smaller than the partition threshold.
7. An IPv6 address generation method, comprising:
the IPv6 address generation model obtained by the IPv6 address generation model creation method of any one of claims 1-6 determines the segments contained in the IPv6 address to be generated;
determining a value of the segment; wherein the value of a segment is determined by the values of the preceding segments with which it is associated and the corresponding conditional probabilities; the conditional probability is a probability that the value of the segment occurs on the condition that the value of the preceding segment occurs, the value of the conditional probability being obtained from the IPv6 address generation model obtained by the IPv6 address generation model creation method according to any one of claims 1 to 6;
after the values of all the segments are determined, the segments are combined in sequence to form the IPv6 address.
8. An IPv6 address generation model creation apparatus, comprising:
the IPv6 address segmentation module is used for counting the occurrence frequency of different values on each address bit in the IPv6 address according to the collected multiple IPv6 addresses, and calculating the uncertainty of each address bit value according to the occurrence frequency of the different values; segmenting the IPv6 address according to uncertainty of values of all address bits in the IPv6 address to obtain a plurality of segments; wherein, the uncertainty of each address bit value in the same segmentation segment is close;
the clustering module is used for respectively clustering the value space of each segmentation segment of the IPv6 address to obtain the probability distribution of all clustering clusters in each segmentation segment;
the IPv6 address generation model training module is used for constructing and training an IPv6 address generation model according to the segmentation segments of the IPv6 address and the probability distribution of all cluster clusters in each segmentation segment; the IPv6 address generation model reflects the segments contained by IPv6 addresses and the conditional probability values between the segments.
9. The IPv6 address generation model creation apparatus of claim 8, further comprising: and the IPv6 address collection module collects IPv6 addresses and obtains the collected multiple IPv6 addresses.
10. The IPv6 address generative model creation device according to claim 8 or 9, wherein the clustering module clusters the value space of each segment of the IPv6 address using a density clustering algorithm, to obtain the probability distribution of all clusters in each segment.
11. The IPv6 address generative model creation device according to claim 8 or 9, wherein the IPv6 address generative model training module constructs and trains a bayesian network-based IPv6 address generative model according to the segments of the IPv6 address and the probability distribution of all cluster clusters within each segment.
12. The IPv6 address generative model creation device according to claim 11, wherein the IPv6 address generative model training module constructs and trains a bayesian network-based IPv6 address generative model according to the segments of the IPv6 address and the probability distribution of all cluster within each segment, and includes:
constructing a Bayesian network structure, wherein the Bayesian network structure reflects the segments contained in the IPv6 address and the incidence relation among the segments;
constructing a probability distribution model of the Bayesian network structure, wherein the probability distribution model reflects the dependency relationship among the segmentation sections; and training the probability distribution model according to the probability distribution of all the clustering clusters in each segmentation segment, so that the parameters in the probability distribution model conform to the probability distribution of all the clustering clusters in each segmentation segment, and obtaining the conditional probability value between the segmentation segments.
13. The IPv6 address generation model creation apparatus according to claim 8 or 9, wherein the IPv6 address segmentation module describes uncertainty of each address bit value using an information entropy, the larger the entropy of the information entropy is, the larger the uncertainty is;
the information entropy is used for partitioning the IPv6 address, and the position with large change of the information entropy value of adjacent address bits is taken as a partitioning point, and the method comprises the following steps: finding out the maximum difference a between the information entropies of all adjacent address bits in the IPv6 address, taking 1/2 of a as a partition threshold value, and taking the position between the two adjacent address bits as a partition point if the information entropy change condition of the two adjacent address bits exceeds the partition threshold value;
the uncertainty of the values of the address bits in the same partition is close, which means that the difference of the information entropies of the adjacent address bits in the same partition is smaller than the partition threshold.
14. An IPv6 address generating apparatus, comprising:
a segment generation module, configured to determine a segment included in the IPv6 address to be generated according to the IPv6 address generation model obtained by the IPv6 address generation model creation apparatus according to any one of claims 8 to 13;
a segment-valued module to determine a value of the segment; wherein the value of a segment is determined by the values of the preceding segments with which it is associated and the corresponding conditional probabilities; the conditional probability is a probability that the value of the segment occurs on the condition that the value of the preceding segment occurs, the value of the conditional probability being obtained from the IPv6 address generation model obtained by the IPv6 address generation model creation means of any one of claims 8 to 13;
and the segmentation section combination module is used for combining the segmentation sections according to the sequence after the values of all the segmentation sections are determined to form the IPv6 address.
15. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the IPv6 address generation model creation method according to any one of claims 1 to 6 or implements the steps of the IPv6 address generation method according to claim 7.
16. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of the IPv6 address generation model creation method according to any one of claims 1 to 6, or performs the steps of the IPv6 address generation method according to claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910943931.8A CN110809066A (en) | 2019-09-30 | 2019-09-30 | IPv6 address generation model creation method, device and address generation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910943931.8A CN110809066A (en) | 2019-09-30 | 2019-09-30 | IPv6 address generation model creation method, device and address generation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110809066A true CN110809066A (en) | 2020-02-18 |
Family
ID=69488314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910943931.8A Pending CN110809066A (en) | 2019-09-30 | 2019-09-30 | IPv6 address generation model creation method, device and address generation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110809066A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432043A (en) * | 2020-03-09 | 2020-07-17 | 清华大学 | Dynamic IPv6 address detection method based on density |
| CN111885213A (en) * | 2020-06-09 | 2020-11-03 | 中国科学院信息工程研究所 | IPv6 address discovery method and device based on gated convolution variational self-encoder |
| CN112651227A (en) * | 2020-11-24 | 2021-04-13 | 中国科学院信息工程研究所 | IPv6 target generation method and device based on language modeling under vector space |
| CN113630482A (en) * | 2021-08-23 | 2021-11-09 | 南京莱克贝尔信息技术有限公司 | IPv6 rapid detection method based on hidden semi-Markov |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102340551A (en) * | 2010-07-27 | 2012-02-01 | 中国电信股份有限公司 | Method and system for establishing IPv6 (Internet Protocol Version 6) address pool |
| US20170359227A1 (en) * | 2016-06-09 | 2017-12-14 | Akamai Technologies, Inc. | Internet address structure analysis, and applications thereof |
| CN109905497A (en) * | 2019-03-05 | 2019-06-18 | 长沙学院 | A kind of IPv6 active address Dynamic Discovery method |
-
2019
- 2019-09-30 CN CN201910943931.8A patent/CN110809066A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102340551A (en) * | 2010-07-27 | 2012-02-01 | 中国电信股份有限公司 | Method and system for establishing IPv6 (Internet Protocol Version 6) address pool |
| US20170359227A1 (en) * | 2016-06-09 | 2017-12-14 | Akamai Technologies, Inc. | Internet address structure analysis, and applications thereof |
| CN109905497A (en) * | 2019-03-05 | 2019-06-18 | 长沙学院 | A kind of IPv6 active address Dynamic Discovery method |
Non-Patent Citations (2)
| Title |
|---|
| FOREMSKI P, PLONKA D, BERGER A.: "Entropy/IP: Uncovering Structure in IPv6 Addresses", 《ACM INTERNET MEASUREMENT CONFERENCE》 * |
| 左志昊等: "活跃IPv6地址前缀的预测算法", 《通信学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111432043A (en) * | 2020-03-09 | 2020-07-17 | 清华大学 | Dynamic IPv6 address detection method based on density |
| CN111432043B (en) * | 2020-03-09 | 2021-06-01 | 清华大学 | Dynamic IPv6 address detection method based on density |
| CN111885213A (en) * | 2020-06-09 | 2020-11-03 | 中国科学院信息工程研究所 | IPv6 address discovery method and device based on gated convolution variational self-encoder |
| CN112651227A (en) * | 2020-11-24 | 2021-04-13 | 中国科学院信息工程研究所 | IPv6 target generation method and device based on language modeling under vector space |
| CN113630482A (en) * | 2021-08-23 | 2021-11-09 | 南京莱克贝尔信息技术有限公司 | IPv6 rapid detection method based on hidden semi-Markov |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110809066A (en) | IPv6 address generation model creation method, device and address generation method | |
| CN110138764B (en) | Attack path analysis method based on hierarchical attack graph | |
| CN112640380B (en) | Apparatus and method for anomaly detection of an input stream of events | |
| CN109194707B (en) | Distributed graph embedding method and device | |
| Papadopoulos et al. | Network mapping by replaying hyperbolic growth | |
| US11652709B2 (en) | Managing computation load in a fog network | |
| CN110135603B (en) | Power network alarm space characteristic analysis method based on improved entropy weight method | |
| CN112085125A (en) | Missing value filling method based on linear self-learning network, storage medium and system | |
| CN115358487A (en) | Federal learning aggregation optimization system and method for power data sharing | |
| CN110838072A (en) | Social network influence maximization method and system based on community discovery | |
| CN113489619A (en) | Network topology inference method and device based on time series analysis | |
| Edunov et al. | Darwini: Generating realistic large-scale social graphs | |
| Liu et al. | Finding densest lasting subgraphs in dynamic graphs: A stochastic approach | |
| CN116681104A (en) | Model building and realizing method of distributed space diagram neural network | |
| CN106022936B (en) | Community structure-based influence maximization algorithm applicable to thesis cooperative network | |
| Al-Saedi et al. | Reducing communication overhead of federated learning through clustering analysis | |
| WO2011114135A1 (en) | Detecting at least one community in a network | |
| US11914956B1 (en) | Unusual score generators for a neuro-linguistic behavioral recognition system | |
| Bekkerman et al. | Heuristic approximation method for a random flow of events by an MC-flow with arbitrary number of states | |
| Chandio et al. | Towards adaptable and tunable cloud-based map-matching strategy for GPS trajectories | |
| CN114492849B (en) | Model updating method and device based on federal learning | |
| CN111917589B (en) | Power communication network resource backup method and related device | |
| Xu et al. | Dm-KDE: dynamical kernel density estimation by sequences of KDE estimators with fixed number of components over data streams | |
| CN115168326A (en) | Hadoop big data platform distributed energy data cleaning method and system | |
| CN114036029A (en) | Disk space usage prediction method and device for server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200218 |